Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 36 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0005

Data Index: 1302117 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0005

Data Index: 403124 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0184. Min Act: -0.0005

Data Index: 821876 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0184. Min Act: -0.0005

Data Index: 1101687 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0183. Min Act: -0.0005

Data Index: 1328911 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0183. Min Act: -0.0005

Data Index: 278331 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0178. Min Act: -0.0005

Data Index: 101531 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0178. Min Act: -0.0005

Data Index: 1194866 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0182. Min Act: -0.0005

Data Index: 848045 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0181. Min Act: -0.0005

Data Index: 24401 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0181. Min Act: -0.0005

Data Index: 776806 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0177. Min Act: -0.0005

Data Index: 424466 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0180. Min Act: -0.0005

Data Index: 493944 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0180. Min Act: -0.0005

Data Index: 282867 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0179. Min Act: -0.0005

Data Index: 666207 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0175. Min Act: -0.0005

Data Index: 702844 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0182. Min Act: -0.0005

Data Index: 535832 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0178. Min Act: -0.0005

Data Index: 379448 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0178. Min Act: -0.0005

Data Index: 28562 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0177. Min Act: -0.0005

Data Index: 1066644 (C4 (Web Text))

Max Activating Token Index: 149